A distributed snapshot protocol for efficient artificial intelligence computation in cloud computing environments

Jong Beom Lim, Joon Min Gil, Heon Chang Yu

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)

Abstract

Many artificial intelligence applications often require a huge amount of computing resources. As a result, cloud computing adoption rates are increasing in the artificial intelligence field. To support the demand for artificial intelligence applications and guarantee the service level agreement, cloud computing should provide not only computing resources but also fundamental mechanisms for efficient computing. In this regard, a snapshot protocol has been used to create a consistent snapshot of the global state in cloud computing environments. However, the existing snapshot protocols are not optimized in the context of artificial intelligence applications, where large-scale iterative computation is the norm. In this paper, we present a distributed snapshot protocol for efficient artificial intelligence computation in cloud computing environments. The proposed snapshot protocol is based on a distributed algorithm to run interconnected multiple nodes in a scalable fashion. Our snapshot protocol is able to deal with artificial intelligence applications, in which a large number of computing nodes are running. We reveal that our distributed snapshot protocol guarantees the correctness, safety, and liveness conditions.

Original languageEnglish
Article number30
JournalSymmetry
Volume10
Issue number1
DOIs
Publication statusPublished - 2018 Jan 1

Bibliographical note

Publisher Copyright:
© 2018 by the authors.

Keywords

  • Artificial intelligence
  • Cloud computing
  • Iterative computation
  • Snapshot protocol

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Chemistry (miscellaneous)
  • General Mathematics
  • Physics and Astronomy (miscellaneous)

Fingerprint

Dive into the research topics of 'A distributed snapshot protocol for efficient artificial intelligence computation in cloud computing environments'. Together they form a unique fingerprint.

Cite this